Artificial neural network model for identifying taxi gross emitter from remote sensing data of vehicle emission

Vehicle emission has been the major source of air pollution in urban areas in the past two decades. This article proposes an artificial neural network model for identifying the taxi gross emitters based on the remote sensing data. After carrying out the field test in Guangzhou and analyzing various factors from the emission data, the artificial neural network modeling was proved to be an advisable method of identifying the gross emitters. On the basis of the principal component analysis and the selection of algorithm and architecture, the Back-Propagation neural network model with 8-17-1 architecture was established as the optimal approach for this purpose. It gave a percentage of hits of 93%. Our previous research result and the result from aggression analysis were compared, and they provided respectively the percentage of hits of 81.63% and 75%. This comparison demonstrates the potentiality and validity of the proposed method in the identification of taxi gross emitters.     

城市生态经济系统模型构建与分析

根据城市生态经济系统(UrbanEco-economicSystem,UEES)运行规律和系统调控的目标,建立了UEES指标体系.以宁波市为例,采用偏最小二乘算法构建了UEES模型.本例中,模型的Q2cum值为0·996,表明其具有较好的稳定性和预测能力.计算结果表明,到2007年、2012年和2020年,宁波市国内生产总值将分别达到2588×108元、3250×108元、5261×108元;万元国内生产总值能耗、城市化水平与产业结构是影响经济规模扩大的主要因素,万元工业产值废水排放量和SO2排放量与经济规模呈显著的负相关关系.在此基础上,提出了宁波生态市建设过程中经济发展的若干建议.     

黑河中下游防风固沙功能时空变化及影响因子分析

黑河中下游是我国重要的防风固沙生态功能区,分析该区域的防风固沙功能时空变化,明确其主要的影响因子贡献,对于指导荒漠化防治、维护流域生态安全十分重要.该研究基于修正风蚀方程(revised wind erosion equation,RWEQ)、一元线性回归斜率分析、灰色关联分析和GIS技术,分析了2000—2017年黑河中下游防风固沙功能动态变化及其影响因子.结果表明:①2000—2017年,黑河中下游年均防风固沙量为3.2×109 t,年均防风固沙功能约为2.44×104 t/km2;防风固沙量总体呈增强趋势,年均增加6.67×107 t,年均变化率为1.85%.②区域防风固沙功能呈现中游较强,向下游递减的空间分布特征,防风固沙功能较高区约占研究区面积的31.54%,一般区占20.77%,较低区(北部荒漠区)占47.69%;甘肃省张掖市和嘉峪关市防风固沙功能呈增加趋势,回归方程系数(slope)为0~26.29%,占总面积的12.51%;额济纳旗东北部和甘肃省高台县中部防风固沙功能呈下降趋势,回归方程系数为-17.17%~0,占总面积的23.30%.③防风固沙功能主要影响因子中,风力因子最主要,贡献率为30.04%,其次为积雪覆盖、土壤湿度、植被覆盖,贡献率分别为24.57%、24.26%和21.13%.研究显示,防风固沙工程应综合考虑气候变化、植被覆盖、土壤特性及人类活动的复合影响,实行具有空间差异化的方案.      

Stepwise multiple regression method of greenhouse gas emission modeling in the energy sector in Poland

The energy sector in Poland is the source of 81% of greenhouse gas (GHG) emissions. Poland, among other European Union countries, occupies a leading position with regard to coal consumption. Polish energy sector actively participates in efforts to reduce GHG emissions to the atmosphere, through a gradual decrease of the share of coal in the fuel mix and development of renewable energy sources. All evidence which completes the knowledge about issues related to GHG emissions is a valuable source of information. The article presents the results of modeling of GHG emissions which are generated by the energy sector in Poland. For a better understanding of the quantitative relationship between total consumption of primary energy and greenhouse gas emission, multiple stepwise regression model was applied. The modeling results of CO₂ emissions demonstrate a high relationship (0.97) with the hard coal consumption variable. Adjustment coefficient of the model to actual data is high and equal to 95%. The backward step regression model, in the case of CH₄ emission, indicated the presence of hard coal (0.66), peat and fuel wood (0.34), solid waste fuels, as well as other sources (− 0.64) as the most important variables. The adjusted coefficient is suitable and equals R² = 0.90. For N₂O emission modeling the obtained coefficient of determination is low and equal to 43%. A significant variable influencing the amount of N₂O emission is the peat and wood fuel consumption.     

基于机器学习的电热防除冰表面温度变化趋势预测

针对飞机部件周期控制律电加热防除冰的应用,提出基于机器学习以预测电加热防除冰表面温度的变化趋势.依靠大型结冰风洞及其电加热防除冰控制系统完成防除冰试验,获得有效的试验数据,以通、断电周期为分割单元,将试验数据划分成验证集和训练集.根据电热防除冰过程的换热情况,构建样本的特征参数,利用机器学习的有监督学习方式,选择KNN...     

研发投入对我国上市环保企业绩效的影响分析

研发投入是技术创新的基础,而创新是一个企业的核心竞争力,直接影响企业的效益及发展。选取2016—2019年我国沪深两市环保行业61家上市公司连续4年的面板数据作为研究对象,采用多元回归分析的方法实证分析环保上市公司研发投入对公司绩效的影响,并分析研发投入的滞后效应。结果显示:研发资金投入强度在当期对公司绩效有负向作用,在滞后一期时与资产收益率呈正相关,滞后两期时与主营业务利润率呈正相关;而研发人员投入强度对企业绩效在当期就有促进作用。为促进企业高质量发展,应当加大研发资金长期性投入,提升研发人员创新能力,加强研发成果转化。     

Predictive Model of Avian Electrocution Risk on Overhead Power Lines

Electrocution on overhead power structures negatively affects avian populations in diverse ecosystems worldwide, contributes to the endangerment of raptor populations in Europe and Africa, and is a major driver of legal action against electric utilities in North America. We investigated factors associated with avian electrocutions so poles that are likely to electrocute a bird can be identified and retrofitted prior to causing avian mortality. We used historical data from southern California to identify patterns of avian electrocution by voltage, month, and year to identify species most often killed by electrocution in our study area and to develop a predictive model that compared poles where an avian electrocution was known to have occurred (electrocution poles) with poles where no known electrocution occurred (comparison poles). We chose variables that could be quantified by personnel with little training in ornithology or electric systems. Electrocutions were more common at distribution voltages (≤33 kV) and during breeding seasons and were more commonly reported after a retrofitting program began. Red‐tailed Hawks (Buteo jamaicensis) (n = 265) and American Crows (Corvus brachyrhynchos) (n = 258) were the most commonly electrocuted species. In the predictive model, 4 of 14 candidate variables were required to distinguish electrocution poles from comparison poles: number of jumpers (short wires connecting energized equipment), number of primary conductors, presence of grounding, and presence of unforested unpaved areas as the dominant nearby land cover. When tested against a sample of poles not used to build the model, our model distributed poles relatively normally across electrocution‐risk values and identified the average risk as higher for electrocution poles relative to comparison poles. Our model can be used to reduce avian electrocutions through proactive identification and targeting of high‐risk poles for retrofitting. Modelo Predictivo del Riesgo de Electrocución de Aves en Líneas Eléctricas Elevadas     

供水管网铁释放的影响因素相对重要性分析

供水管网的铁释放问题近年来日益受到关注.影响供水管网铁释放的因素众多,本研究选取了pH、溶解氧(DO)、碱度(Alk)、硬度、氯离子(Cl~-)、硫酸根(SO_4~(2-))、温度(T)和水力停留时间(HRT)这8个影响因素,利用逐步回归和偏相关分析,建立了铁释放的非线性幂指数模型,并用标准化回归系数和偏相关系数比较了这些因素的相对重要性.结果表明,铁释放模型拟合效果良好;用标准化回归系数衡量影响因素相对重要性时,SO_4~(2-)、HRT、Cl~-和T是相对重要的因素,相对重要性排序为SO_4~(2-)≈HRTCl~-T;用偏相关系数衡量时,HRT、SO_4~(2-)、Alk、Cl~-和T是相对重要的因素,排序为HRTSO_4~(2-)AlkCl~-T.综合两种系数的分析结果,HRT、SO_4~(2-)和Cl~-是本研究条件下相对重要的因素,T和Alk的相对重要性视实际情况变动.     

基于GIS和LUR模型的西安市PM2.5浓度空间分布模拟研究

基于地理信息系统GIS和土地利用回归LUR模型,模拟西安市PM2.5浓度空间动态分布,结果表明:与PM2.5浓度相关性最高的分别为缓冲区为2 km的水域面积、人口密度和距离水域距离,R 2分别为0.501,0.393和0.280;与PM2.5浓度相关性最低的分别为缓冲区为4 km的水域面积、未利用地面积和耕地面积,R 2分别为0.039、0.021和0.017.未考虑风速建立的LUR模型多元回归的相关系数为0.856,R 2为0.733,考虑风速的相关系数为0.892,R 2为0.796,表明风速对于污染物的分布影响较大,LUR模型模拟效果较好.模拟的PM2.5年均浓度高风险区分布于中部,中风险区分布于中西部,低风险区分布于东南部和西部.     

ABC算法优化SVR的磨损故障预测模型

目的为了提高故障预测的精度,针对支持向量回归SVR(Support vector machine for regression,SVR)参数选择困难的问题,提出一种采用人工蜂群(artificial bee colony,ABC)算法优化支持向量回归(SVR)的故障预测模型(ABC-SVR)。方法该模型先对样本数据进行重构,然后将故障预测误差(适应度)作为优化目标,通过ABC算法寻优找到最优的SVR参数,建立故障预测模型。最后通过实例仿真验证模型的优越性。结果采用ABC算法优化的SVR故障预测模型进行时间序列预测,能够较好地跟踪发动机滑油金属元素浓度的变化过程,并且能够提前2个取样时间预测异常情况的出现。结论 ABC-SVR模型有效解决了SVR参数选择难题,能够更加准确地表现故障变化规律,提高了故障预测精度。